Multi-focus image fusion through pixel-wise voting and morphology

Multi-focus image fusion (MFIf) aims to fuse two or more images into one image, so that the fused image contains more information. This paper proposes a new multi-focus image fusion based on pixel-wise voting and morphology. Firstly, we perform sliding window on the multi-focus image and calculate the gray-scale variance of each sliding window. Then, the voting matrix of each pixel is obtained by comparing the sliding window gray-scale variance. Next, a multi-focus decision map (IFM) is obtained through voting. At the same time, morphological operations can further denoise the IFM and achieve a better image fusion effect. Finally, we also use the weighting method for boundary optimization to get the better fused image. We conducted experiments on ”books”, ”flower”, ”newspaper”, ”lytro” and ”aymaz” datasets. Comparing with other 10 fusion algorithms, the experimental results demonstrate that our proposed multi-focus image fusion method can achieve a good fusion effect.